Related papers: DSTEA: Improving Dialogue State Tracking via Entit…

Learning high-quality dialogue representations is essential for solving a variety of dialogue-oriented tasks, especially considering that dialogue systems often suffer from data scarcity. In this paper, we introduce Dialogue Sentence…

Prompt-based methods with large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks. These models improve even further with the addition of a few labeled in-context exemplars to guide output…

We present our work on Track 4 in the Dialogue System Technology Challenges 8 (DSTC8). The DSTC8-Track 4 aims to perform dialogue state tracking (DST) under the zero-shot settings, in which the model needs to generalize on unseen service…

In schema-guided dialogue state tracking models estimate the current state of a conversation using natural language descriptions of the service schema for generalization to unseen services. Prior generative approaches which decode slot…

Maintaining engagement and consistency is particularly important in dialogue systems. Existing works have improved the performance of dialogue systems by intentionally learning interlocutor personas with sophisticated network structures.…

We present a multi-modal dialogue system for interactive learning of perceptually grounded word meanings from a human tutor. The system integrates an incremental, semantic parsing/generation framework - Dynamic Syntax and Type Theory with…

Open domain entity state tracking aims to predict reasonable state changes of entities (i.e., [attribute] of [entity] was [before_state] and [after_state] afterwards) given the action descriptions. It's important to many reasoning tasks to…

Creating multilingual task-oriented dialogue (TOD) agents is challenging due to the high cost of training data acquisition. Following the research trend of improving training data efficiency, we show for the first time, that in-context…

Domain adaptation has recently become a key problem in dialogue systems research. Deep learning, while being the preferred technique for modeling such systems, works best given massive training data. However, in the real-world scenario,…

Dialog response generation in open domain is an important research topic where the main challenge is to generate relevant and diverse responses. In this paper, we propose a new dialog pre-training framework called DialogVED, which…

Slot filling is a fundamental task in dialog state tracking in task-oriented dialog systems. In multi-domain task-oriented dialog system, user utterances and system responses may mention multiple named entities and attributes values. A…

Pre-training methods with contrastive learning objectives have shown remarkable success in dialog understanding tasks. However, current contrastive learning solely considers the self-augmented dialog samples as positive samples and treats…

End-to-End Speech Translation (E2E-ST) is the task of translating source speech directly into target text bypassing the intermediate transcription step. The representation discrepancy between the speech and text modalities has motivated…

Recently, speech-text pre-training methods have shown remarkable success in many speech and natural language processing tasks. However, most previous pre-trained models are usually tailored for one or two specific tasks, but fail to conquer…

In a human-machine dialog scenario, deciding the appropriate time for the machine to take the turn is an open research problem. In contrast, humans engaged in conversations are able to timely decide when to interrupt the speaker for…

This paper examines various unsupervised pretraining objectives for learning dialog context representations. Two novel methods of pretraining dialog context encoders are proposed, and a total of four methods are examined. Each pretraining…

Neural language models (LM) trained on diverse corpora are known to work well on previously seen entities, however, updating these models with dynamically changing entities such as place names, song titles and shopping items requires…

Motivated by the success of pre-trained language models such as BERT in a broad range of natural language processing (NLP) tasks, recent research efforts have been made for adapting these models for different application domains. Along this…

This paper presents Structure Aware Dense Retrieval (SANTA) model, which encodes user queries and structured data in one universal embedding space for retrieving structured data. SANTA proposes two pretraining methods to make language…

Fine-tuning on generalized tasks such as instruction following, code generation, and mathematics has been shown to enhance language models' performance on a range of tasks. Nevertheless, explanations of how such fine-tuning influences the…